Geekbench AI Score

4990
Single Precision Score
45111
Half Precision Score
60226
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User nvsnvs32
Upload Date March 19 2026 09:45 PM
Views 4

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M5 Pro
System Information
Operating System macOS 26.3.1 (Build 25D2128)
Model Mac17,9
Model IDMac17,9
Motherboard Mac17,9
CPU Information
Name Apple M5 Pro
Topology 1 Processor, 15 Cores
Identifier Apple M5 Pro
Base Frequency 4.60 GHz
Cluster 15 Cores
Cluster 210 Cores
Memory Information
Size 24.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2326
432.6 IPS
 
Image Classification (HP)
100% 21378
3.98 KIPS
 
Image Classification (Q)
97% 26182
4.89 KIPS
 
Image Segmentation (SP)
100% 2502
40.6 IPS
 
Image Segmentation (HP)
100% 26272
425.9 IPS
 
Image Segmentation (Q)
99% 37218
603.3 IPS
 
Pose Estimation (SP)
100% 10432
12.2 IPS
 
Pose Estimation (HP)
100% 184074
214.8 IPS
 
Pose Estimation (Q)
95% 340440
399.0 IPS
 
Object Detection (SP)
100% 2806
222.6 IPS
 
Object Detection (HP)
100% 23667
1.88 KIPS
 
Object Detection (Q)
91% 28515
2.28 KIPS
 
Face Detection (SP)
100% 5149
61.2 IPS
 
Face Detection (HP)
100% 49937
593.4 IPS
 
Face Detection (Q)
100% 69700
828.2 IPS
 
Depth Estimation (SP)
100% 9349
72.0 IPS
 
Depth Estimation (HP)
99% 138882
1.07 KIPS
 
Depth Estimation (Q)
85% 211951
1.66 KIPS
 
Style Transfer (SP)
100% 26941
34.6 IPS
 
Style Transfer (HP)
100% 287877
370.1 IPS
 
Style Transfer (Q)
96% 399271
515.2 IPS
 
Image Super-Resolution (SP)
100% 6042
223.1 IPS
 
Image Super-Resolution (HP)
100% 66204
2.44 KIPS
 
Image Super-Resolution (Q)
99% 105770
3.91 KIPS
 
Text Classification (SP)
100% 2986
3.99 KIPS
 
Text Classification (HP)
99% 5526
7.38 KIPS
 
Text Classification (Q)
93% 5464
7.33 KIPS
 
Machine Translation (SP)
100% 2404
41.4 IPS
 
Machine Translation (HP)
100% 19531
336.4 IPS
 
Machine Translation (Q)
98% 19472
336.5 IPS
 

Compare

Set Baseline Geekbench 6 now available